- * As of Lucene version 3.1, this class implements the Word Break rules from the - * Unicode Text Segmentation algorithm, as specified in - * Unicode Standard Annex #29. - *
- *Many applications have specific tokenizer needs. If this tokenizer does - * not suit your application, please consider copying this source code - * directory to your project and maintaining your own grammar-based tokenizer. - * - * - *
You must specify the required {@link Version} - * compatibility when creating StandardTokenizer: - *
input to the newly created JFlex scanner.
- *
- * @param input The input reader
- *
- * See http://issues.apache.org/jira/browse/LUCENE-1068
- */
- public StandardTokenizer(Version matchVersion, Reader input) {
- super();
- init(input, matchVersion);
- }
-
- /**
- * Creates a new StandardTokenizer with a given {@link AttributeSource}.
- */
- public StandardTokenizer(Version matchVersion, AttributeSource source, Reader input) {
- super(source);
- init(input, matchVersion);
- }
-
- /**
- * Creates a new StandardTokenizer with a given {@link org.apache.lucene.util.AttributeSource.AttributeFactory}
- */
- public StandardTokenizer(Version matchVersion, AttributeFactory factory, Reader input) {
- super(factory);
- init(input, matchVersion);
- }
-
- private final void init(Reader input, Version matchVersion) {
- if (matchVersion.onOrAfter(Version.LUCENE_34)) {
- this.scanner = new StandardTokenizerImpl(input);
- } else if (matchVersion.onOrAfter(Version.LUCENE_31)) {
- this.scanner = new StandardTokenizerImpl31(input);
- } else {
- this.scanner = new ClassicTokenizerImpl(input);
- }
- if (matchVersion.onOrAfter(Version.LUCENE_24)) {
- replaceInvalidAcronym = true;
- } else {
- replaceInvalidAcronym = false;
- }
- this.input = input;
- }
-
- // this tokenizer generates three attributes:
- // term offset, positionIncrement and type
- private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
- private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
- private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
- private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
-
- /*
- * (non-Javadoc)
- *
- * @see org.apache.lucene.analysis.TokenStream#next()
- */
- @Override
- public final boolean incrementToken() throws IOException {
- clearAttributes();
- int posIncr = 1;
-
- while(true) {
- int tokenType = scanner.getNextToken();
-
- if (tokenType == StandardTokenizerInterface.YYEOF) {
- return false;
- }
-
- if (scanner.yylength() <= maxTokenLength) {
- posIncrAtt.setPositionIncrement(posIncr);
- scanner.getText(termAtt);
- final int start = scanner.yychar();
- offsetAtt.setOffset(correctOffset(start), correctOffset(start+termAtt.length()));
- // This 'if' should be removed in the next release. For now, it converts
- // invalid acronyms to HOST. When removed, only the 'else' part should
- // remain.
- if (tokenType == StandardTokenizer.ACRONYM_DEP) {
- if (replaceInvalidAcronym) {
- typeAtt.setType(StandardTokenizer.TOKEN_TYPES[StandardTokenizer.HOST]);
- termAtt.setLength(termAtt.length() - 1); // remove extra '.'
- } else {
- typeAtt.setType(StandardTokenizer.TOKEN_TYPES[StandardTokenizer.ACRONYM]);
- }
- } else {
- typeAtt.setType(StandardTokenizer.TOKEN_TYPES[tokenType]);
- }
- return true;
- } else
- // When we skip a too-long term, we still increment the
- // position increment
- posIncr++;
- }
- }
-
- @Override
- public final void end() {
- // set final offset
- int finalOffset = correctOffset(scanner.yychar() + scanner.yylength());
- offsetAtt.setOffset(finalOffset, finalOffset);
- }
-
- @Override
- public void reset(Reader reader) throws IOException {
- super.reset(reader);
- scanner.yyreset(reader);
- }
-
- /**
- * Prior to https://issues.apache.org/jira/browse/LUCENE-1068, StandardTokenizer mischaracterized as acronyms tokens like www.abc.com
- * when they should have been labeled as hosts instead.
- * @return true if StandardTokenizer now returns these tokens as Hosts, otherwise false
- *
- * @deprecated Remove in 3.X and make true the only valid value
- */
- @Deprecated
- public boolean isReplaceInvalidAcronym() {
- return replaceInvalidAcronym;
- }
-
- /**
- *
- * @param replaceInvalidAcronym Set to true to replace mischaracterized acronyms as HOST.
- * @deprecated Remove in 3.X and make true the only valid value
- *
- * See https://issues.apache.org/jira/browse/LUCENE-1068
- */
- @Deprecated
- public void setReplaceInvalidAcronym(boolean replaceInvalidAcronym) {
- this.replaceInvalidAcronym = replaceInvalidAcronym;
- }
-}